English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Research into methods for improving the performance of large language models(LLMs) through fine-tuning, retrieval-augmented generation (RAG) andsoft-prompting has tended to focus on the use of highly technical or high-costtechniques, making many of the newly discovered approaches comparativelyinaccessible to non-technical users. In this paper we tested an unmodifiedversion of GPT 3.5, a fine-tuned version, and the same unmodified model whengiven access to a vectorised RAG database, both in isolation and in combinationwith a basic, non-algorithmic soft prompt. In each case we tested the model'sability to answer a set of 100 questions relating primarily to events thatoccurred after September 2021 (the point at which GPT 3.5's training data setends). We found that if commercial platforms are used and default settings areapplied with no iteration in order to establish a baseline set of outputs, afine-tuned model outperforms GPT 3.5 Turbo, while the RAG approachout-performed both. The application of a soft prompt significantly improved theperformance of each approach.

Establishing Performance Baselines in Fine-Tuning, Retrieval-Augmented Generation and Soft-Prompting for Non-Specialist LLM Users